Enough AI copilots, we need AI HUDs • Hacker News Board

Re: Enough AI copilots, we need AI HUDs

#161

Post by Cthulhu_ » Mon, Jul 28, 2025, 9:56 AM UTC

JimDabell wrote: post #29

callc wrote: post #25

Earlier quoted context omitted.

Humans writing the test first and LLM writing the code is much better than the reverse. And that is because tests are simply the “truth” and “intention” of the code as a contract. When you give up the work of deciding what the expected inputs and outputs of the code/program is you are no longer in the drivers seat.

> When you give up the work of deciding what the expected inputs and outputs of the code/program is you are no longer in the drivers seat. You don’t need to write tests for that, you need to write acceptance criteria.

What are tests but repeatable assertions of said acceptance criteria?

Re: Enough AI copilots, we need AI HUDs

#162

Post by Cthulhu_ » Mon, Jul 28, 2025, 9:59 AM UTC

William_BB wrote: post #80

motorest wrote: post #76

Earlier quoted context omitted.

> There's no way this would work for any serious C++ codebase. Compile times alone make this impossible There's nothing in C++ that prevents this. If build times are your bogeyman, you'd be pleased to know that all mainstream build systems support incremental builds.

The original example was (paraphrasing) "rerunning 10-100 tests that take 1ms after each keystroke". Even with incremental builds, that surely does not sound plausible? I only mentioned C++ because that's my main working language, but this wouldn't sound reasonable for Rust either, no?

It doesn't sound reasonable for any language tbh, tests don't run that fast and running after each keystroke instead of on save or after a debouncing delay is just wasteful. If you amortize / ignore run times, load, and ignore the annoyance of tests blinking red/green at every keystroke then I suppose it would be alright.

Re: Enough AI copilots, we need AI HUDs

#163

Post by Cthulhu_ » Mon, Jul 28, 2025, 10:02 AM UTC

ravila4 wrote: post #56

I think one key reason HUDs haven’t taken off more broadly is the fundamental limitation of our current display medium - computer screens and mobile devices are terrible at providing ambient, peripheral information without being intrusive. When I launch an AI agent to fix a bug or handle a complex task, there’s this awkward wait time where it takes too long for me to sit there staring at the screen waiting for output…

The only real life usage of any kind of HUD I can imagine at the moment is navigation, and I have only ever used that (or other car related things) as something I selectively look at, never felt like it's something I need to have in sight at all times.

That said, the best GUI is the one you don't notice, so uh... I can't actually name anything else, it's probably deeply engrained in my computer usage.

Re: Enough AI copilots, we need AI HUDs

#164

Post by Cthulhu_ » Mon, Jul 28, 2025, 10:05 AM UTC

est wrote: post #122

It's like the magic moment when GUIs replace CLIs. I remember the first time I started up Win95 from DOS days. Stunning.

Or terminal GUIs in DOS. Before (and during) Windows, our go-to was 3DMENU [0] for starting up games and the like.

[0] https://archive.org/details/3DMENUPLUSDOS

Re: Enough AI copilots, we need AI HUDs

#165

Post by Cthulhu_ » Mon, Jul 28, 2025, 10:06 AM UTC

amelius wrote: post #114

I want an AI HUD that blocks ads.

What if you could get AR glasses that translates ads into their core message like "CONSUME", "MARRY AND REPRODUCE" and "OBEY"? That would be cool. You could make a movie out of that!

Re: Enough AI copilots, we need AI HUDs

#166

Post by teoremma » Mon, Jul 28, 2025, 10:10 AM UTC

smolder wrote: post #152

teoremma wrote: post #150

Earlier quoted context omitted.

How so? I seriously don't follow what you are trying to convey

[flagged]

And the narrative they didn't like was what again?

Re: Enough AI copilots, we need AI HUDs

#167

Post by atoav » Mon, Jul 28, 2025, 10:13 AM UTC

smolder wrote: post #128

furyofantares wrote: post #68

I'm very curious if a toggle would be useful that would display a heatmap of a source file showing how surprising each token is to the model. Red tokens are more likely to be errors, bad names, or wrong comments.

[flagged]

You're adding nothing of substance. If you have a point about the subject itself make it and present the receipts, then the rest of us can decide if we can follow your observation.

Without even knowing what the lines of the supposed conflict ought to be about: All I see here are baseless accusations from your side that make you quite frankly look a little bit unhinged. Please discuss your issues based on the merit of ideas not based on accusations and persons.

Re: Enough AI copilots, we need AI HUDs

#168

Post by sokoloff » Mon, Jul 28, 2025, 10:16 AM UTC

smolder wrote: post #155

vidarh wrote: post #153

Earlier quoted context omitted.

What I understand is that if this has already gotten two of your comments killed, and will eventually get your account banned if you keep it up. I'm only bothering with this at all because I see from your profile that you make reasonable comments quite regularly.

Consider that I'm being reasonable.

It’s frequently possible to disagree while still adding to the discussion.

The comments of yours that I see downvoted are falling well short of that mark, particularly the ones where you accuse a decade-plus-old account with a recent comment history of being quite skeptical or even anti-LLM for coding of being a shill for an AI company.

Consider that your words are not being experienced as reasonable by readers.

Re: Enough AI copilots, we need AI HUDs

#169

Post by quantumHazer » Mon, Jul 28, 2025, 10:17 AM UTC

callc wrote: post #25

cadamsdotcom wrote: post #4

Love the idea & spitballing ways to generalize to coding.. Thought experiment: as you write code, an LLM generates tests for it & the IDE runs those tests as you type, showing which ones are passing & failing, updating in real time. Imagine 10-100 tests that take The tests could appear in a separated panel next to your code, and pass/fail status in the gutter of that panel. As simple as red and green dots for tests t…

Humans writing the test first and LLM writing the code is much better than the reverse. And that is because tests are simply the “truth” and “intention” of the code as a contract. When you give up the work of deciding what the expected inputs and outputs of the code/program is you are no longer in the drivers seat.

I disagree. You can simply code in a way that all test passes and you have more problem than before reviewing the code that is being generated.

Re: Enough AI copilots, we need AI HUDs

#170

Post by motorest » Mon, Jul 28, 2025, 10:17 AM UTC

JimDabell wrote: post #113

motorest wrote: post #100

Earlier quoted context omitted.

> I know about BDD frameworks. I’m talking higher level than that. What level do you think there is above "Given I'm logged in as a Regular User When I go to the front page Then I see the Profile button"?

The line you wrote does not describe a feature. Typically you have many of those cases and they collectively describe one feature. I’m talking about describing the feature. Do you seriously think there is no higher level than given/when/thens?

> The line you wrote does not describe a feature.

I'm describing a scenario as implemented in a gherkin feature file. A feature is tracked by one or more scenarios.

https://cucumber.io/docs/gherkin/reference/

> Do you seriously think there is no higher level than given/when/thens?

You tell me which higher level you have in mind.